Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Session

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    increment
    -0.07
    魅力
    -0.07
     KY
    -0.07
     bugün
    -0.07
    國際
    -0.07
    庙
    -0.06
    半年
    -0.06
     Completed
    -0.06
    !!!↵↵
    -0.06
    .modify
    -0.06
    POSITIVE LOGITS
    praak
    0.08
    ationToken
    0.08
    눙
    0.08
    wać
    0.07
    asta
    0.07
     handleSubmit
    0.07
    wallet
    0.07
    pekt
    0.07
     подготовк
    0.07
     chaired
    0.07
    Act Density 0.005%

    No Known Activations